AB openclaw-hot-skills
Discover trending, must-have, and topic-specific high-value skills from ClawHub. Use when the user asks to see hot/popular/trending OpenClaw skills, wants a ranked shortlist of worth-installing skills, asks what skills are popular recently, wants a must-have install list, wants help finding popular skills for a specific theme such as PDF, GitHub, knowledge base, browser automation, speech-to-text, docs, search, or productivity, or says things like "帮我找个 skill", "有没有这种 skill", "有什么值得装的 skill", "最近有什么好用的 skill", or "怎么扩展能力". Also use when the output should include ClawHub links and whether each skill is already installed locally.
As a process B 73/100 · Nearly there — weak spots: inputs and preconditions
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 73/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Steps. 123 steps
- 100Failures and branches. 19 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2206 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low The skill ranks results itself: that belongs to the system behind the tool, not the model
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 635: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 123 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.